Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3843 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1924350 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6927. Min Act: -0.0000

Data Index: 377928 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6233. Min Act: -0.0000

Data Index: 881270 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1462836 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1647561 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6452. Min Act: -0.0000

Data Index: 308370 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6061. Min Act: -0.0000

Data Index: 350212 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6258. Min Act: -0.0000

Data Index: 387647 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1125071 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5894. Min Act: -0.0000

Data Index: 112455 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6031. Min Act: -0.0000

Data Index: 541290 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1703142 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5307. Min Act: -0.0000

Data Index: 411560 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1381307 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1442749 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1071297 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5479. Min Act: -0.0000

Data Index: 244381 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5645. Min Act: -0.0000

Data Index: 917958 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1577379 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5579. Min Act: -0.0000

Data Index: 284024 (The Pile)

Max Activating Token Index: 877